Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    emotions and opinions related to personal experiences and interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances where individuals or small entities are referred to in a larger context or group

    oai_token-act-pair · gpt-3.5-turboTriggered by @jordan
    New Auto-Interp
    Negative Logits
    alysis
    -0.72
     sorts
    -0.68
    aeda
    -0.68
     Contracts
    -0.65
     Arrows
    -0.64
    Ü
    -0.63
    hement
    -0.63
    nature
    -0.62
    nance
    -0.61
    ModLoader
    -0.61
    POSITIVE LOGITS
     apiece
    0.77
     subp
    0.77
     staffer
    0.76
    anooga
    0.76
    hander
    0.72
    ](
    0.68
    acre
    0.67
    anza
    0.66
    inkle
    0.66
     summed
    0.66
    Act Density 10.911%

    No Known Activations